Check blackness in github actions (pdfminer#711)

* Check blackness in github actions

* Blacken code

* Update github action names

* Add contributing guidelines on using black

* Add to checklist for PR

.flake8

@@ -0,0 +1,5 @@
+[flake8]
+max-line-length = 88
+extend-ignore = 
+    # See https://github.com/PyCQA/pycodestyle/issues/373
+    E203,

.github/pull_request_template.md

@@ -1,22 +1,17 @@
 **Pull request**
 
-Thanks for improving pdfminer.six! Please include the following information to
-help us discuss and merge this PR:
-
-- A description of why this PR is needed. What does it fix? What does it 
-  improve?
-- A summary of the things that this PR changes.
-- Reference the issues that this PR fixes (use the fixes #(issue nr) syntax). 
-  If this PR does not fix any issue, create the issue first and mention that 
-  you are willing to work on it.
+Please remove this paragraph and replace it with a description of your PR.
+Also include links to the issues that it fixes. 
 
 **How Has This Been Tested?**
 
-Please describe the tests that you ran to verify your changes. Provide 
-instructions so we can reproduce. Include an example pdf if you have one. 
+Please repalce this paragraph with a description of how this PR has been 
+tested. Include the necessary instructions and files such that other can
+reproduce it.
 
 **Checklist**
 
+- [ ] I have formatted my code with [black](https://github.com/psf/black).
 - [ ] I have added tests that prove my fix is effective or that my feature 
   works
 - [ ] I have added docstrings to newly created methods and classes

.github/workflows/actions.yml

@@ -15,6 +15,15 @@ env:
 
 jobs:
 
+  check-code-formatting:
+    name: Check code formatting
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+      - name: Check code formatting
+        uses: psf/black@stable
+
   check-coding-style:
     name: Check coding style
     runs-on: ubuntu-latest

CONTRIBUTING.md

@@ -31,7 +31,7 @@ Any contribution is appreciated! You might want to:
 * Include unit tests when possible. In case of bugs, this will help to prevent the same mistake in the future. In case 
   of features, this will show that your code works correctly.
 * Code should work for Python 3.6+.
-* Code should conform to PEP8 coding style.
+* Code should be formatted with [black](https://github.com/psf/black). 
 * New features should be well documented using docstrings.
 * Check spelling and grammar.
 * Don't forget to update the [CHANGELOG.md](CHANGELOG.md#[Unreleased])
@@ -68,3 +68,9 @@ Any contribution is appreciated! You might want to:
    ```sh
     nox -e py36
     ```
+
+4. After changing the code, run the black formatter.
+
+    ```sh
+    black .
+    ```

docs/source/conf.py

@@ -16,14 +16,13 @@
 
 import pdfminer
 
-sys.path.insert(0, os.path.join(
-    os.path.abspath(os.path.dirname(__file__)), '../../'))
+sys.path.insert(0, os.path.join(os.path.abspath(os.path.dirname(__file__)), "../../"))
 
 # -- Project information -----------------------------------------------------
 
-project = 'pdfminer.six'
-copyright = '2019, Yusuke Shinyama, Philippe Guglielmetti & Pieter Marsman'
-author = 'Yusuke Shinyama, Philippe Guglielmetti & Pieter Marsman'
+project = "pdfminer.six"
+copyright = "2019, Yusuke Shinyama, Philippe Guglielmetti & Pieter Marsman"
+author = "Yusuke Shinyama, Philippe Guglielmetti & Pieter Marsman"
 
 # The full version, including alpha/beta/rc tags
 release = pdfminer.__version__
@@ -35,16 +34,16 @@
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    'sphinxarg.ext',
-    'sphinx.ext.autodoc',
-    'sphinx.ext.doctest',
+    "sphinxarg.ext",
+    "sphinx.ext.autodoc",
+    "sphinx.ext.doctest",
 ]
 
 # Root rst file
-master_doc = 'index'
+master_doc = "index"
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
@@ -57,9 +56,9 @@
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'alabaster'
+html_theme = "alabaster"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]

noxfile.py

@@ -6,53 +6,30 @@
 
 @nox.session
 def lint(session):
-    session.install('flake8')
-    session.run(
-        'flake8',
-        'pdfminer/',
-        'tools/',
-        'tests/',
-        '--count',
-        '--statistics'
-    )
+    session.install("flake8")
+    session.run("flake8", "pdfminer/", "tools/", "tests/", "--count", "--statistics")
 
 
 @nox.session
 def types(session):
-    session.install('mypy')
+    session.install("mypy")
     session.run(
-        'mypy',
-        '--install-types',
-        '--non-interactive',
-        '--show-error-codes',
-        '.'
+        "mypy", "--install-types", "--non-interactive", "--show-error-codes", "."
     )
 
 
 @nox.session(python=PYTHON_ALL_VERSIONS)
 def tests(session):
     session.install("-e", ".[dev]")
-    session.run('pytest')
+    session.run("pytest")
 
 
 @nox.session
 def docs(session):
     session.install("-e", ".[docs]")
     session.run(
-        'python',
-        '-m',
-        'sphinx',
-        '-b',
-        'html',
-        'docs/source',
-        'docs/build/html'
+        "python", "-m", "sphinx", "-b", "html", "docs/source", "docs/build/html"
     )
     session.run(
-        'python',
-        '-m',
-        'sphinx',
-        '-b',
-        'doctest',
-        'docs/source',
-        'docs/build/doctest'
+        "python", "-m", "sphinx", "-b", "doctest", "docs/source", "docs/build/doctest"
     )

pdfminer/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '20211012'
+__version__ = "20211012"
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     print(__version__)

pdfminer/_saslprep.py

@@ -18,7 +18,7 @@
 
 """An implementation of RFC4013 SASLprep."""
 
-__all__ = ['saslprep']
+__all__ = ["saslprep"]
 
 import stringprep
 from typing import Callable, Tuple
@@ -37,7 +37,8 @@
     stringprep.in_table_c6,
     stringprep.in_table_c7,
     stringprep.in_table_c8,
-    stringprep.in_table_c9)
+    stringprep.in_table_c9,
+)
 
 
 def saslprep(data: str, prohibit_unassigned_code_points: bool = True) -> str:
@@ -63,12 +64,12 @@ def saslprep(data: str, prohibit_unassigned_code_points: bool = True) -> str:
     in_table_c12 = stringprep.in_table_c12
     in_table_b1 = stringprep.in_table_b1
     data = "".join(
-        ["\u0020" if in_table_c12(elt) else elt
-         for elt in data if not in_table_b1(elt)])
+        ["\u0020" if in_table_c12(elt) else elt for elt in data if not in_table_b1(elt)]
+    )
 
     # RFC3454 section 2, step 2 - Normalize
     # RFC4013 section 2.2 normalization
-    data = unicodedata.ucd_3_2_0.normalize('NFKC', data)
+    data = unicodedata.ucd_3_2_0.normalize("NFKC", data)
 
     in_table_d1 = stringprep.in_table_d1
     if in_table_d1(data[0]):
@@ -89,7 +90,6 @@ def saslprep(data: str, prohibit_unassigned_code_points: bool = True) -> str:
     # RFC3454 section 2, step 3 and 4 - Prohibit and check bidi
     for char in data:
         if any(in_table(char) for in_table in prohibited):
-            raise ValueError(
-                "SASLprep: failed prohibited character check")
+            raise ValueError("SASLprep: failed prohibited character check")
 
     return data

pdfminer/arcfour.py

@@ -9,7 +9,6 @@
 
 
 class Arcfour:
-
     def __init__(self, key: Sequence[int]) -> None:
         # because Py3 range is not indexable
         s = [i for i in range(256)]
@@ -24,12 +23,12 @@ def __init__(self, key: Sequence[int]) -> None:
     def process(self, data: bytes) -> bytes:
         (i, j) = (self.i, self.j)
         s = self.s
-        r = b''
+        r = b""
         for c in iter(data):
-            i = (i+1) % 256
-            j = (j+s[i]) % 256
+            i = (i + 1) % 256
+            j = (j + s[i]) % 256
             (s[i], s[j]) = (s[j], s[i])
-            k = s[(s[i]+s[j]) % 256]
+            k = s[(s[i] + s[j]) % 256]
             r += bytes((c ^ k,))
         (self.i, self.j) = (i, j)
         return r

pdfminer/ascii85.py

@@ -21,30 +21,30 @@ def ascii85decode(data: bytes) -> bytes:
 
     """
     n = b = 0
-    out = b''
+    out = b""
     for i in iter(data):
         c = bytes((i,))
-        if b'!' <= c and c <= b'u':
+        if b"!" <= c and c <= b"u":
             n += 1
-            b = b*85+(ord(c)-33)
+            b = b * 85 + (ord(c) - 33)
             if n == 5:
-                out += struct.pack('>L', b)
+                out += struct.pack(">L", b)
                 n = b = 0
-        elif c == b'z':
+        elif c == b"z":
             assert n == 0, str(n)
-            out += b'\0\0\0\0'
-        elif c == b'~':
+            out += b"\0\0\0\0"
+        elif c == b"~":
             if n:
-                for _ in range(5-n):
-                    b = b*85+84
-                out += struct.pack('>L', b)[:n-1]
+                for _ in range(5 - n):
+                    b = b * 85 + 84
+                out += struct.pack(">L", b)[: n - 1]
             break
     return out
 
 
 # asciihexdecode(data)
-hex_re = re.compile(br'([a-f\d]{2})', re.IGNORECASE)
-trail_re = re.compile(br'^(?:[a-f\d]{2}|\s)*([a-f\d])[\s>]*$', re.IGNORECASE)
+hex_re = re.compile(rb"([a-f\d]{2})", re.IGNORECASE)
+trail_re = re.compile(rb"^(?:[a-f\d]{2}|\s)*([a-f\d])[\s>]*$", re.IGNORECASE)
 
 
 def asciihexdecode(data: bytes) -> bytes:
@@ -57,15 +57,16 @@ def asciihexdecode(data: bytes) -> bytes:
     the EOD marker after reading an odd number of hexadecimal digits, it
     will behave as if a 0 followed the last digit.
     """
+
     def decode(x: bytes) -> bytes:
         i = int(x, 16)
         return bytes((i,))
 
-    out = b''
+    out = b""
     for x in hex_re.findall(data):
         out += decode(x)
 
     m = trail_re.search(data)
     if m:
-        out += decode(m.group(1)+b'0')
+        out += decode(m.group(1) + b"0")
     return out